metadata
base_model: akbarsigit/llama3.1-sft-r256-a512-merged-16bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- kto
license: apache-2.0
language:
- en
Uploaded model
- Developed by: akbarsigit
- License: apache-2.0
- Finetuned from model : akbarsigit/llama3.1-sft-r256-a512-merged-16bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.